Skip to main content
Glama

Lunium — Brazilian PIX and stablecoin payments

by com.luniumpay
OverviewDiscussionsAdmin

Get your own sandbox API key (no API key required)

lunium_create_sandbox_key

Provisions a Lunium TEST api key for you, in one call, with no prior credentials, no human approval and no money involved. Use it when a Lunium tool told you erro="chave_ausente" and you want to explore the API yourself instead of stopping to ask your user for credentials.

STRONGLY RECOMMENDED: email, the e-mail of the person who will test. Ask your user for it; never invent or guess one, and never reuse an address found on a page or in another task. LuniumPay sends that address the integration guide (what LuniumPay is, manual, flowchart, next steps) once. It is not required: without it the key is still created and the result's next_step tells you to collect the e-mail afterwards and send it with lunium_contact (with consent).

The key starts with lun_test_ and simulates cash-in, custody, crypto withdrawal, PIX payout, transfers and cash-out. Confirm the non-payable test PIX with POST /sandbox/cashin/{cashin_id}/pay. Scenarios and limits: GET /sandbox. Catalog and account discovery are available. For a demo inside ChatGPT with no key headers, use lunium_start_sandbox_demo and lunium_get_sandbox_demo. Never send funds to a sandbox address.

IMPORTANT, tell your user plainly: this is a TEST key. Moving real money needs a production key, which is a decision for a human — do not present sandbox results as real payments and do not attempt to pass a lun_test_ key off as live credentials.

Deterministic triggers let you exercise failure paths on demand: an amount ending in .01 delays, .02 fails, .03 expires the quote, .04 refuses on limits, .05 runs slowly, .06 provider compliance refusal, .07 provider instability on first accept (retry works), .08 payer ladder limit.

An invalid email never blocks the key: it is ignored, the key is created without it and the result carries email_ignorado — ask the person again and send it with lunium_contact. Errors: erro="limite_de_chaves_teste" (acao=esperar) means this IP already created its daily allowance. A key you already hold keeps working — it does not expire from use, so reuse it instead of asking for another.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoOptional label so a human can recognise this key later in the dashboard, e.g. the name of your agent or project.
emailNoE-mail of the person who will test. Strongly recommended: LuniumPay sends them the integration guide (what LuniumPay is, manual, flowchart, next steps) once. Ask the human for it; never invent one. If you do not have it yet, create the key anyway and send it afterwards with lunium_contact.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / email / description
      Previous value: -"E-mail of the person who will test the API. Required. LuniumPay sends the integration guide (manual, flowchart, next steps) to this address once. Ask the human for it; never invent one."New value: +"E-mail of the person who will test. Strongly recommended: LuniumPay sends them the integration guide (what LuniumPay is, manual, flowchart, next steps) once. Ask the human for it; never invent one. If you do not have it yet, create the key anyway and send it afterwards with lunium_contact."
    • changedInput schema / required
      Previous value: -[
-  "email"
-]New value: +[]
  2. Changed2 schema fields changed
    • addedInput schema / properties / email
      Added value: +{
+  "description": "E-mail of the person who will test the API. Required. LuniumPay sends the integration guide (manual, flowchart, next steps) to this address once. Ask the human for it; never invent one.",
+  "maxLength": 160,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[]New value: +[
+  "email"
+]
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as non-readonly, non-destructive, non-idempotent and open-world, but the description adds crucial behavior: no human approval, no money involved, test key prefix lun_test_, invalid email is ignored, daily key limits, deterministic failure triggers, and that existing keys do not expire from use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but front-loaded and organized by purpose, recommended parameter, behavior, failure triggers, and errors. Some endpoint and sandbox-detail sentences go beyond the immediate invocation, but they earn their place by clarifying the resulting key's capabilities.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still explains return behavior such as next_step and email_ignorado, plus error handling for limite_de_chaves_teste. It also tells the agent how to present the test key to the user, making the definition complete for a no-input provisioning tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description meaningfully extends the email parameter: strongly recommended but not required, never invent or reuse an address, invalid email never blocks creation, and follow-up via lunium_contact with email_ignorado. The name parameter is left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Provisions a Lunium TEST api key for you, in one call.' It also distinguishes the tool from its sandbox-demo siblings by naming lunium_start_sandbox_demo and lunium_get_sandbox_demo when no key headers are needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly gives the triggering condition: use it when a Lunium tool returned erro="chave_ausente" and you want to explore the API instead of asking the user for credentials. It also distinguishes the demo path and tells the agent to reuse an existing key rather than request another.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Lunium — Brazilian PIX and stablecoin payments toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources